BKM1804/Meta-Llama-3-8B-9a92f7c8-ca32-4e22-819f-f4d7824a8b05-DPO_cosine_with_min_lr_beta_01 Updated Jul 9, 2025
BKM1804/llama2-7b-koNqa-test-v1-7e7bd06e-53a5-4ff0-8d54-5e0d177018b9-DPO_cosine_with_min_lr_beta_01 Updated Jul 9, 2025
BKM1804/Meta-Llama-3-8B-9a92f7c8-ca32-4e22-819f-f4d7824a8b05-SFT_DPO_cosine_with_min_lr_beta_03 Updated Jul 9, 2025
BKM1804/Meta-Llama-3-8B-9a92f7c8-ca32-4e22-819f-f4d7824a8b05-SFT_DPO_cosine_with_min_lr_beta_01 Updated Jul 9, 2025
BKM1804/llama2-7b-koNqa-test-v1-7e7bd06e-53a5-4ff0-8d54-5e0d177018b9-SFT_DPO_cosine_with_min_lr_beta_03 Updated Jul 9, 2025
BKM1804/llama2-7b-koNqa-test-v1-7e7bd06e-53a5-4ff0-8d54-5e0d177018b9-SFT_DPO_cosine_with_min_lr_beta_01 Updated Jul 9, 2025 • 1
BKM1804/llama-2-7b-f3d32b04-8b6b-4bcb-a84e-9fd5edc8797a-SFT_DPO_ratio_1_cosine_with_min_lr-dpo-tuned Updated Jul 8, 2025
BKM1804/llama-2-7b-f3d32b04-8b6b-4bcb-a84e-9fd5edc8797a-SFT_DPO_ratio_1_cosine_with_min_lr Text Generation • 7B • Updated Jul 8, 2025 • 2
BKM1804/open_llama_3b-2c8684c1-2e85-49f6-98ee-3a27b8b152d9_SFT_DPO_ratio_1_cosine_with_min_lr Updated Jul 4, 2025
BKM1804/Qwen1.5-0.5B-Chat-baeb9d28-6195-46a8-9968-3df7b7f0ff95-SFT_DPO_ratio_2_cosine Text Generation • 0.5B • Updated Jul 3, 2025 • 1
BKM1804/SmolLM-135M-Instruct-7f2d96e5-ea2d-4eda-9c50-d70025b2b0a7-SFT_DPO_ratio_025_cosine Text Generation • 0.1B • Updated Jul 3, 2025 • 1
BKM1804/Qwen1.5-0.5B-Chat-baeb9d28-6195-46a8-9968-3df7b7f0ff95-SFT_DPO_ratio_025_cosine Text Generation • 0.5B • Updated Jul 2, 2025 • 1
BKM1804/SmolLM-135M-Instruct-7f2d96e5-ea2d-4eda-9c50-d70025b2b0a7-SFT_DPO_ratio_2_cosine Text Generation • 0.1B • Updated Jul 2, 2025 • 1
BKM1804/gpt-neo-1.3B-e9e17474-330c-458e-a3ae-8a4e42f7f3ea-SFT_DPO_ratio_2_cosine Text Generation • 1B • Updated Jul 2, 2025
BKM1804/Qwen2.5-1.5B-c3e84fc4-a240-46cf-a3b9-1df0b49bba6a-SFT_DPO_ratio_2_cosine Text Generation • 2B • Updated Jul 2, 2025 • 1
BKM1804/gpt-neo-1.3B-e9e17474-330c-458e-a3ae-8a4e42f7f3ea-SFT_DPO_ratio_025_cosine Text Generation • 1B • Updated Jul 2, 2025
BKM1804/Qwen2.5-1.5B-c3e84fc4-a240-46cf-a3b9-1df0b49bba6a-SFT_DPO_ratio_025_cosine Text Generation • 2B • Updated Jul 2, 2025 • 1
BKM1804/zephyr-7b-beta-5a259b13-5311-4621-b3d3-606580904a91-DPO_ratio_1_WSDS Text Generation • 7B • Updated Jul 2, 2025
BKM1804/Yarn-Llama-2-7b-128k-f26c8b32-0c66-41f0-81e3-7805f787b9c0-DPO_ratio_1_WSDS Text Generation • 7B • Updated Jul 1, 2025 • 1
BKM1804/zephyr-7b-beta-996cae5f-262b-48e3-8183-39a39a0a527a-DPO_ratio_1_WSDS Text Generation • 7B • Updated Jul 1, 2025 • 1
BKM1804/zephyr-sft-45033763-7303-4063-84dc-70aaf438589a-SFT_DPO_ratio_0_25_cosine_with_min_lr Text Generation • 7B • Updated Jun 30, 2025 • 1
BKM1804/zephyr-7b-beta-996cae5f-262b-48e3-8183-39a39a0a527a-DPO_ratio_0_5_WSDS Text Generation • 7B • Updated Jun 30, 2025 • 1
BKM1804/zephyr-sft-6e20b394-8949-4b3d-b719-d99263f793e3-DPO_ratio_0_25_WSDS Text Generation • 7B • Updated Jun 30, 2025 • 1
BKM1804/tinyllama-chat-6e20b394-8949-4b3d-b719-d99263f793e3-SFT_DPO_ratio_0_25_cosine_with_min_lr Text Generation • 1B • Updated Jun 30, 2025 • 1